Let us help you find the training program you are looking for.

If you can't find what you are looking for, contact us, we'll help you find it. We have over 800 training programs to choose from.


Course Skill Level:

Foundational to Intermediate

Course Duration:

2 day/s

  • Course Delivery Format:

    Live, instructor-led.

  • Course Category:

    AI / Machine Learning

  • Course Code:


Who should attend & recommended skills:

Those with intermediate Python, Linux, math, & ML experience looking for concepts & tools to build reactive computer vision systems

Who should attend & recommended skills

  • This course is geared for Python developers, analysts, or others with Python skills who wish to get concepts and tools for building intelligent, scalable computer vision systems that can identify and react to objects in images, videos, and real life.
  • Skill-level: Foundation-level Deep Learning for Vision Systems skills for Intermediate skilled team members. This is not a basic class.
  • Python: Intermediate (3-5 years’ experience)
  • Math: Intermediate (3-5 years’ experience)
  • Machine Learning: Intermediate (3-5 years’ experience)
  • Matplotlib: Basic (1-2 years’ experience) helpful, not required
  • Pandas Machine Learning Libraries: Basic (1-2 years’ experience) helpful, not required
  • Linux: Basic (1-2 years’ experience), including familiarity with command-line options such as ls, cd, cp, and su

About this course

Deep Learning for Vision Systems teaches you to apply deep learning techniques to solve real-world computer vision problems. In his straightforward and accessible style, DL and CV expert Mohamed Elgendy introduces you to the concept of visual intuition; how a machine learns to understand what it sees. Then you will explore the DL algorithms used in different CV applications. You will drill down into the different parts of the CV interpreting system, or pipeline. Using Python, OpenCV, Keras, TensorFlow, and Amazons Mx Net, you will discover advanced DL techniques for solving CV problems. Applications of focus include image classification, segmentation, captioning, and generation as well as face recognition and analysis. You will also cover the most important deep learning architectures including artificial neural networks (ANNs), convolutional networks (CNNs), and recurrent networks (RNNs), knowledge that you can apply to related deep learning disciplines like natural language processing and voice user interface. Real-life, scalable projects from Amazon, Google, and Facebook drive it all home. With this invaluable course, you will gain the essential skills for building amazing end-to-end CV projects that solve real-world problems.

Skills acquired & topics covered

  • Working in a hands-on learning environment, led by our Deep Learning expert instructor, students will learn about and explore:
  • The DL algorithms used in different CV applications
  • Drilling down into the different parts of the CV interpreting system, or pipeline using Python, OpenCV, Keras, TensorFlow, and Amazons Mx Net
  • Discovering advanced DL techniques for solving CV problems
  • Introduction to computer vision
  • Deep learning and neural networks
  • Transfer learning and advanced CNN architectures
  • Image classification and captioning
  • Object detection with YOLO, SSD and R-CNN
  • Style transfer
  • AI ethics
  • Real-world projects

Course breakdown / modules

  • Computer vision intuition
  • Applications of computer vision
  • Computer Vision Pipeline – The big picture
  • Input image
  • Image preprocessing
  • Feature extraction
  • Classifier learning algorithm
  • Ch summary and takeaways

  • The Perceptron intuition
  • Multi-Layer Perceptron (MLP)
  • Activation functions
  • Feedforward
  • Error functions
  • Optimization algorithms
  • Backpropagation
  • Ch summary and takeaways
  • Project: Build Your first Neural Network

  • Image classification using MLP
  • CNNs Architecture
  • Basic components of the CNN
  • Image classification using CNNs
  • Add Dropout layers to avoid overfitting
  • Convolution over colored images (3D images)
  • Ch summary and takeaways
  • Project: Image classification for colored images (CIFAR-10 dataset)

  • Define the performance metrics
  • Design a baseline model
  • Get your data ready for training
  • Evaluate the model and interpret its performance (error analysis)
  • Improve the network and tune hyperparameters
  • Batch normalization (BN)
  • Ch summary and takeaways
  • Project: Achieve >90% accuracy on the CIFAR-10 image classification project

  • CNN design patterns
  • LeNet-5
  • VGGNet
  • Inception and Google Net
  • Res Net

  • What are the problems that transfer learning is solving?
  • What is transfer learning?
  • How transfer learning works
  • Transfer learning approaches
  • Choose the appropriate level of transfer learning
  • Open-source datasets
  • Ch summary and takeaways
  • Project 1: A pretrained network as a feature extractor
  • Project 2: Fine tuning

  • General object detection framework
  • Region-Based Convolutional Neural Networks (R-CNNs)
  • Single Shot Detection (SSD)
  • Ch summary and takeaways

  • GANs Architecture
  • Evaluate GAN models
  • Popular GANs Applications
  • Building your own GAN project

  • How convolutional neural networks see the world
  • Deep Dream
  • Neural Style Transfer